File: resnet50.py

package info (click to toggle)
keras-applications 1.0.8%2Bds-1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 600 kB
  • sloc: python: 3,490; makefile: 11; sh: 3
file content (297 lines) | stat: -rw-r--r-- 11,888 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
"""ResNet50 model for Keras.

# Reference:

- [Deep Residual Learning for Image Recognition](
    https://arxiv.org/abs/1512.03385) (CVPR 2016 Best Paper Award)

Adapted from code contributed by BigMoyan.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import warnings

from . import get_submodules_from_kwargs
from . import imagenet_utils
from .imagenet_utils import decode_predictions
from .imagenet_utils import _obtain_input_shape

preprocess_input = imagenet_utils.preprocess_input

WEIGHTS_PATH = ('https://github.com/fchollet/deep-learning-models/'
                'releases/download/v0.2/'
                'resnet50_weights_tf_dim_ordering_tf_kernels.h5')
WEIGHTS_PATH_NO_TOP = ('https://github.com/fchollet/deep-learning-models/'
                       'releases/download/v0.2/'
                       'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5')

backend = None
layers = None
models = None
keras_utils = None


def identity_block(input_tensor, kernel_size, filters, stage, block):
    """The identity block is the block that has no conv layer at shortcut.

    # Arguments
        input_tensor: input tensor
        kernel_size: default 3, the kernel size of
            middle conv layer at main path
        filters: list of integers, the filters of 3 conv layer at main path
        stage: integer, current stage label, used for generating layer names
        block: 'a','b'..., current block label, used for generating layer names

    # Returns
        Output tensor for the block.
    """
    filters1, filters2, filters3 = filters
    if backend.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = layers.Conv2D(filters1, (1, 1),
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2a')(input_tensor)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = layers.Activation('relu')(x)

    x = layers.Conv2D(filters2, kernel_size,
                      padding='same',
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2b')(x)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = layers.Activation('relu')(x)

    x = layers.Conv2D(filters3, (1, 1),
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2c')(x)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    x = layers.add([x, input_tensor])
    x = layers.Activation('relu')(x)
    return x


def conv_block(input_tensor,
               kernel_size,
               filters,
               stage,
               block,
               strides=(2, 2)):
    """A block that has a conv layer at shortcut.

    # Arguments
        input_tensor: input tensor
        kernel_size: default 3, the kernel size of
            middle conv layer at main path
        filters: list of integers, the filters of 3 conv layer at main path
        stage: integer, current stage label, used for generating layer names
        block: 'a','b'..., current block label, used for generating layer names
        strides: Strides for the first conv layer in the block.

    # Returns
        Output tensor for the block.

    Note that from stage 3,
    the first conv layer at main path is with strides=(2, 2)
    And the shortcut should have strides=(2, 2) as well
    """
    filters1, filters2, filters3 = filters
    if backend.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = layers.Conv2D(filters1, (1, 1), strides=strides,
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2a')(input_tensor)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = layers.Activation('relu')(x)

    x = layers.Conv2D(filters2, kernel_size, padding='same',
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2b')(x)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = layers.Activation('relu')(x)

    x = layers.Conv2D(filters3, (1, 1),
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2c')(x)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = layers.Conv2D(filters3, (1, 1), strides=strides,
                             kernel_initializer='he_normal',
                             name=conv_name_base + '1')(input_tensor)
    shortcut = layers.BatchNormalization(
        axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = layers.add([x, shortcut])
    x = layers.Activation('relu')(x)
    return x


def ResNet50(include_top=True,
             weights='imagenet',
             input_tensor=None,
             input_shape=None,
             pooling=None,
             classes=1000,
             **kwargs):
    """Instantiates the ResNet50 architecture.

    Optionally loads weights pre-trained on ImageNet.
    Note that the data format convention used by the model is
    the one specified in your Keras config at `~/.keras/keras.json`.

    # Arguments
        include_top: whether to include the fully-connected
            layer at the top of the network.
        weights: one of `None` (random initialization),
              'imagenet' (pre-training on ImageNet),
              or the path to the weights file to be loaded.
        input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
            to use as image input for the model.
        input_shape: optional shape tuple, only to be specified
            if `include_top` is False (otherwise the input shape
            has to be `(224, 224, 3)` (with `channels_last` data format)
            or `(3, 224, 224)` (with `channels_first` data format).
            It should have exactly 3 inputs channels,
            and width and height should be no smaller than 32.
            E.g. `(200, 200, 3)` would be one valid value.
        pooling: Optional pooling mode for feature extraction
            when `include_top` is `False`.
            - `None` means that the output of the model will be
                the 4D tensor output of the
                last convolutional block.
            - `avg` means that global average pooling
                will be applied to the output of the
                last convolutional block, and thus
                the output of the model will be a 2D tensor.
            - `max` means that global max pooling will
                be applied.
        classes: optional number of classes to classify images
            into, only to be specified if `include_top` is True, and
            if no `weights` argument is specified.

    # Returns
        A Keras model instance.

    # Raises
        ValueError: in case of invalid argument for `weights`,
            or invalid input shape.
    """
    global backend, layers, models, keras_utils
    backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs)

    if not (weights in {'imagenet', None} or os.path.exists(weights)):
        raise ValueError('The `weights` argument should be either '
                         '`None` (random initialization), `imagenet` '
                         '(pre-training on ImageNet), '
                         'or the path to the weights file to be loaded.')

    if weights == 'imagenet' and include_top and classes != 1000:
        raise ValueError('If using `weights` as `"imagenet"` with `include_top`'
                         ' as true, `classes` should be 1000')

    # Determine proper input shape
    input_shape = _obtain_input_shape(input_shape,
                                      default_size=224,
                                      min_size=32,
                                      data_format=backend.image_data_format(),
                                      require_flatten=include_top,
                                      weights=weights)

    if input_tensor is None:
        img_input = layers.Input(shape=input_shape)
    else:
        if not backend.is_keras_tensor(input_tensor):
            img_input = layers.Input(tensor=input_tensor, shape=input_shape)
        else:
            img_input = input_tensor
    if backend.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1

    x = layers.ZeroPadding2D(padding=(3, 3), name='conv1_pad')(img_input)
    x = layers.Conv2D(64, (7, 7),
                      strides=(2, 2),
                      padding='valid',
                      kernel_initializer='he_normal',
                      name='conv1')(x)
    x = layers.BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
    x = layers.Activation('relu')(x)
    x = layers.ZeroPadding2D(padding=(1, 1), name='pool1_pad')(x)
    x = layers.MaxPooling2D((3, 3), strides=(2, 2))(x)

    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')

    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')

    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')

    x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')

    if include_top:
        x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
        x = layers.Dense(classes, activation='softmax', name='fc1000')(x)
    else:
        if pooling == 'avg':
            x = layers.GlobalAveragePooling2D()(x)
        elif pooling == 'max':
            x = layers.GlobalMaxPooling2D()(x)
        else:
            warnings.warn('The output shape of `ResNet50(include_top=False)` '
                          'has been changed since Keras 2.2.0.')

    # Ensure that the model takes into account
    # any potential predecessors of `input_tensor`.
    if input_tensor is not None:
        inputs = keras_utils.get_source_inputs(input_tensor)
    else:
        inputs = img_input
    # Create model.
    model = models.Model(inputs, x, name='resnet50')

    # Load weights.
    if weights == 'imagenet':
        if include_top:
            weights_path = keras_utils.get_file(
                'resnet50_weights_tf_dim_ordering_tf_kernels.h5',
                WEIGHTS_PATH,
                cache_subdir='models',
                md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
        else:
            weights_path = keras_utils.get_file(
                'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                WEIGHTS_PATH_NO_TOP,
                cache_subdir='models',
                md5_hash='a268eb855778b3df3c7506639542a6af')
        model.load_weights(weights_path)
        if backend.backend() == 'theano':
            keras_utils.convert_all_kernels_in_model(model)
    elif weights is not None:
        model.load_weights(weights)

    return model